Java tutorial
/* * Copyright (c) 2011 Pentaho Corporation. All rights reserved. * This software was developed by Pentaho Corporation and is provided under the terms * of the GNU Lesser General Public License, Version 2.1. You may not use * this file except in compliance with the license. If you need a copy of the license, * please go to http://www.gnu.org/licenses/lgpl-2.1.txt. The Original Code is Pentaho * Data Integration. The Initial Developer is Pentaho Corporation. * * Software distributed under the GNU Lesser Public License is distributed on an "AS IS" * basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. Please refer to * the license for the specific language governing your rights and limitations. */ package org.pentaho.wordcount; import java.io.IOException; import java.util.ArrayList; import java.util.List; import org.apache.hadoop.conf.Configuration; import org.apache.hadoop.conf.Configured; import org.apache.hadoop.fs.Path; import org.apache.hadoop.io.LongWritable; import org.apache.hadoop.io.Text; import org.apache.hadoop.mapred.FileInputFormat; import org.apache.hadoop.mapred.FileOutputFormat; import org.apache.hadoop.mapred.JobClient; import org.apache.hadoop.mapred.JobConf; import org.apache.hadoop.util.Tool; import org.apache.hadoop.util.ToolRunner; import org.pentaho.hadoop.mapreduce.GenericTransReduce; /** * This is an example Hadoop Map/Reduce application. * It reads the text input files, breaks each line into words * and counts them. The output is a locally sorted list of words and the * count of how often they occurred. * * To run: bin/hadoop jar build/hadoop-examples.jar wordcount * [-m <i>maps</i>] [-r <i>reduces</i>] <i>in-dir</i> <i>out-dir</i> */ public class LocalWordCount extends Configured implements Tool { static int printUsage() { System.out.println("wordcount [-m <maps>] [-r <reduces>] <input> <output>"); ToolRunner.printGenericCommandUsage(System.out); return -1; } /** * The main driver for word count map/reduce program. * Invoke this method to submit the map/reduce job. * @throws IOException When there is communication problems with the * job tracker. */ public int run(String[] args) throws Exception { JobConf conf = new JobConf(getConf(), LocalWordCount.class); conf.setJobName("wordcount"); // the keys are words (strings) conf.setOutputKeyClass(Text.class); // the values are counts (ints) conf.setOutputValueClass(LongWritable.class); conf.setMapperClass(Map.class); conf.setCombinerClass(GenericTransReduce.class); conf.setReducerClass(GenericTransReduce.class); // these are set so the job is run in the same // JVM as the debugger - we are not submitting // to MR Node. conf.set("mapred.job.tracker", "local"); conf.set("fs.default.name", "local"); List<String> other_args = new ArrayList<String>(); for (int i = 0; i < args.length; ++i) { try { if ("-m".equals(args[i])) { conf.setNumMapTasks(Integer.parseInt(args[++i])); } else if ("-r".equals(args[i])) { conf.setNumReduceTasks(Integer.parseInt(args[++i])); } else { other_args.add(args[i]); } } catch (NumberFormatException except) { System.out.println("ERROR: Integer expected instead of " + args[i]); return printUsage(); } catch (ArrayIndexOutOfBoundsException except) { System.out.println("ERROR: Required parameter missing from " + args[i - 1]); return printUsage(); } } // Make sure there are exactly 2 parameters left. if (other_args.size() != 2) { System.out.println("ERROR: Wrong number of parameters: " + other_args.size() + " instead of 2."); return printUsage(); } FileInputFormat.setInputPaths(conf, other_args.get(0)); FileOutputFormat.setOutputPath(conf, new Path(other_args.get(1))); JobClient.runJob(conf); return 0; } public static void main(String[] args) throws Exception { int res = ToolRunner.run(new Configuration(), new LocalWordCount(), args); System.exit(res); } }